Physical Layer Communications System Design Over-the-Air Using Adversarial Networks

This paper presents a novel method for synthesizing new physical layer modulation and coding schemes for communications systems using a learning-based approach which does not require an analytic model of the impairments in the channel. It extends prior work published on the channel autoencoderto consider the case where the stochastic channel response is not known or can not be easily modeled in a closed form analytic expression. By adopting an adversarial approach for learning a channel response approximation and information encoding, we jointly learn a solution to both tasks applicable over a wide range of channel environments. We describe the operation of the proposed adversarial system, share results for its training and validation over-the-air, and discuss implications and future work in the area.